Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.

Messages - Stefan

Pages: 1 ... 129 130 [131] 132 133 ... 149
3D-Tech News Around The Web / CUDA Toolkit 3.0 Beta available to public now
« on: November 13, 2009, 03:31:38 PM »
Downloads via developer forums

The Portland Group has announced that release 2010 of the PGI line of high-performance parallelizing compilers and development tools for Linux, Mac OS X, and Windows. PGI 2010 is the first general release to include full support for the PGI Accelerator Programming model v1.0 standard on x64 processor-based systems incorporating NVIDIA CUDA-enabled Graphical Processing Units (GPUs). In addition to supporting high-level programming of accelerators using the PGI Accelerator programming model, the PGI Release 2010 also includes PGI CUDA Fortran, an explicit GPU programming model and API that gives programmers direct control of all aspects of programming NVIDIA GPUs

Full story at Dr. Dobb's

Fire fascinates us. From warmth and cooking to forging tools and managing agriculture, fire is foundational to the human experience. And in the virtual world, it's a big player. It's also quite complex to create.

To help developers with this task, Intel created a framework called Intel® Smoke Game Technology Demo (still free to download and use without restrictions). Included in the demo are Tree and Fire Systems, which are described and illustrated in the white paper below.

Read the White Paper: Procedural Trees and Procedural Fire in a Virtual World

Procedural Trees and Procedural Fire in a Virtual World

    We respond to fire on a primal level and it sparks our adrenaline. But when it comes to realistically rendering it, the challenges are many.

    This white paper demonstrates a technique for realistically animating a forest fire. It describes the creation and implementation of the grammar and parser used to create the trees, and examines the Fire System which uses the Smart Particle Engine to set the trees on fire. Includes screen shots and diagrams, sample scripts, and grammar and parser details.

3D-Tech News Around The Web / Fluid Simulation for Video Games (part 4)
« on: November 11, 2009, 08:52:00 PM »
This article, the fourth in a series, augments a fluid simulation, presented in the third article, to include two-way fluid-body interaction. The first article summarized fluid dynamics, the second surveyed fluid simulation techniques and the third presented a vortex-particle fluid simulation that runs in real time. The additions presented in this article allow the flow to interact with rigid bodies and vice versa.

Full story at Intel

3D-Tech News Around The Web / Is Larrabee For the Rest of Us?
« on: November 11, 2009, 07:30:36 PM »
Can non-numerical application developers take advantage from the new LRBni instructions?

Larrabee, the new multicore processor that Intel will release in the next months, is going to catch most programmers unprepared. For once, it is difficult to estimate its potential on the basis of the very few details available. And programmers of non-numerical developers, traditionally secondary audience for GPGPU architects, are going to face an even steeper programming challenge.

Full story at Dr. Dobb's

3D-Tech News Around The Web / Changes in PhysX (2.8.3) SDK access procedure
« on: November 11, 2009, 07:25:04 PM »
PhysX SDK is still free but no longer available for public download,  to get access to SDK and tools you must register an account at PhysX Developer Support website and wait until it’ll be approved.

Full story at PhysXinfo

3D-Tech News Around The Web / Prometheus for UDK Released
« on: November 08, 2009, 08:07:31 PM »
The Prometheus team has released a standalone build of Prometheus for UDK today. The download clocks in at 331mb and can be grabbed from FileWorks right now.

    Prometheus is a mission-based, single-player co-op game in the spirit of "Portal" and "Mirror's Edge." By using the Prometheus Device, players bend the laws of Einsteinian physics using the theory of quantum states, meaning that goals are accomplished by completing missions with your past, present and future selves. You'll need to keep your wits about you and your memory sharp in solving puzzles presented with this unique game play mechanic. Progression through the story introduces new challenges, with tasks increasing in difficulty, and a final dramatic conclusion questions present loyalties and even your own existence.

    * Download UDK Prometheus from BeyondUnreal FileWorks (321mb)

Fast mirror

3D-Tech News Around The Web / Fraps 3.0.0 released - supports DX11
« on: November 06, 2009, 12:02:49 PM »
5th November 2009 - Fraps 3.0.0 Released

New features and a new look!  Fraps is now compatible with Windows 7 and the latest DirectX 11 games.

Ventrilo & TeamSpeak users have long wanted a way to record their microphone and speakers at the same time.  For Windows 7 and Vista we've added realtime sound mixing to our video recording so you can now capture both sides of the conversation!

NVIDIA have recently included stereoscopic 3D support directly into their drivers.  If you play your DirectX9 (D3D9) game with 3D Vision enabled you can use Fraps to record the game in full 3D too!  You'll get a side-by-side stereo AVI recording that you can drop straight in to a stereoscopic 3D player!

Finally, we are aware that more and more people are putting Fraps to professional use.  We've added a new option to force lossless RGB compression to ensure that you always have the highest quality video output to work with.

We hope that you enjoy Fraps 3!


3.0.0 - 5th Nov 2009
- DirectX 11 support
- Compatible with Windows 7 final (RTM) and RC1 versions
- Stereoscopic 3D Vision video capture up to 1920x1200 for D3D9 games
- Force lossless RGB option to always capture video in pure form
- Ability to mix both game sound and external input such as microphone (Vista/Win7 only)

Cudapad is a software that helps developments develop and test small kernals for NVidia’s© Cuda© language. Sometimes in your IDE you’ll want a quick way build or test a piece of Cuda code and CudaPad lets you do it.  It shows the ptx code, cubin code, register count, error and more on the fly.  There is no need to manually compile your code.

To use cudapad just type or paste some Cuda code in the left panel.  After this is done then the PTX(or Cubin) code is shown in the right window with convenient connector lines that help match up the source code to the PTX code.  Below the PTX code you will see more information about your kernel including memory usage and register usage.  And below the source code window you’ll see code errors.

The framework BehaveRT allows to create a simulation:

    * interactive: by using the power of recent NVIDIA GPUs through CUDA;
    * generalized: by choosing the most suitable simulation engine's modules or by creating custonized ones;
    * renderable: by using OpenGL VBOs (Vertex Buffer Object), the simulation is directly renderable avoiding data transferts between CPU and GPU.

AntiPlanet2 is first person 3D shooter game in fantastic extraterrestrial world, which is built of spheres and shadows. AntiPlanet uses ray tracing render for visualization. It works through CUDA. 3D engine works in any resolution in real-time, supports transparency and bi-cubic textures.

Surprise, surprise! The CUDA version doesn't render geometry on my old 8800GTX  >:(

3D-Tech News Around The Web / OpenCL-z fixed by oscarbg
« on: November 06, 2009, 10:27:59 AM »
Oscar's blog gives you also a lot of informations about the differences in AMD OpenCL, Apple OpenCL, IBM OpenCL and NVIDIA OpenCL  ::)

OpenCL-z by oscarbg

3 November 2009


Works with Nvidia 195.39 OpenCL ICD or higher
Works with CPUs and AMDs GPUs with AMD Stream 2.0beta4 and Catalyst 9.11 or higher
Autodetects in displays info of AMD and Nvidia OpenCL drivers in a single launch in current form..
For detecting AMD drivers you need to define the enviroment variable ATISTREAMSDKROOT where the SDK is  ..
I think in Windows this is done in the installer in Linux use something as

The CUDA Toolkit 3.0 Beta is now available to GPU Computing registered developers.

Highlights for this release include:

    * CUDA Driver / Runtime Buffer Interoperability, which allows applications using the CUDA Driver API to also use libraries implemented using the CUDA C Runtime.
    * A new, separate version of the CUDA C Runtime (CUDART) for debugging in emulation-mode.
    * C++ Class Inheritance and Template Inheritance support for increased programmer productivity
    * A new unified interoperability API for Direct3D and OpenGL, with support for:
          o OpenGL texture interop
          o Direct3D 11 interop support
    * cuda-gdb hardware debugging support for applications that use the CUDA Driver API
    * New CUDA Memory Checker reports misalignment and out of bounds errors, available as a debugging mode within cuda-gdb and also as a stand-alone utility.
    * CUDA Toolkit libraries are now versioned, enabling applications to require a specific version, support multiple versions explicitly, etc.
    * CUDA C/C++ kernels are now compiled to standard ELF format
    * Support for all the OpenCL features in the latest R195.39 beta driver:
          o Double Precision
          o OpenGL Interoperability, for interactive high performance visualization
          o Query for Compute Capability, so you can target optimizations for GPU architectures (cl_nv_device_attribute_query)
          o Ability to control compiler optimization settings, etc. via support for NVIDIA Compiler Flags (cl_nv_compiler_options)
          o OpenCL Images support, for better/faster image filtering
          o 32-bit Atomics for fast, convenient data manipulation
          o Byte Addressable Stores, for faster video/image processing and compression algorithms
          o Support for the latest OpenCL spec revision 48 and latest official Khronos OpenCL headers as of 11/1/2009
    * Early support for the Fermi architecture, including:
          o Native 64-bit GPU support
          o Multiple Copy Engine support
          o ECC reporting
          o Concurrent Kernel Execution
          o Fermi HW debugging support in cuda-gdb

For more information on general purpose computing features of the Fermi architecture, see:

Windows developers should be sure to sign up for the Nexus (codename) beta program, and test drive the integrated support for GPU hardware debugging, profiling, and platform trace/analysis features at:


3D-Tech News Around The Web / Getting GPUs on the grid
« on: November 04, 2009, 06:00:26 PM »
Enhancing the performance of computer clusters and supercomputers using graphical processing units is all the rage. But what happens when you put these chips on a full-fledged grid?

Full story at ISGTW

The Trinigy Engine is one of the first game architectures that utilize DirectX 11 features.
PC Games Hardware shows exclusive screenshots from a tech demo and thus gives a preview on what game graphics of the future might look like.

3D-Tech News Around The Web / DirectCompute Benchmark 0.1
« on: November 03, 2009, 05:38:16 PM »
Benchmark v0.1

First of all:
1) You NEED DirectX 11 installed so for now, it will work only on win7.
2) You DON'T need DX11 hardware, DirectCompute is supported on DX10 class devices if only drivers support it (forceware >= 190.62, Catalyst currently doesn't support DirectCompute on DX10/10.1 GPUs)

Sample results:

GeForce 9800GT ECO OC (740/1800/1010) : M15670/S3600
GeForce 9800GT ECO OC (600/1500/900)  : M13195/S3220

S-single threaded result
M-default dx11 device settings


3D-Tech News Around The Web / D3DGear 3.53 - Added support to DirectX 11
« on: November 03, 2009, 05:32:21 PM »
What is D3DGear?
D3DGear is an advanced Windows ingame utility software for 3D video games. With D3DGear, you can measure ingame framerate (FPS), capture 3D game screenshot, record video game movie. You even can use D3DGear to access Windows desktop within game.

3D-Tech News Around The Web / AMD Display Library (ADL) SDK 2.0 available
« on: November 03, 2009, 05:28:45 PM »
Designed to access display driver functionality for ATI Radeon™ and ATI FirePro™ graphics cards.

    * The SDK supports the Radeon family of GPUs including integrated, discrete and FirePro products.
    * The SDK supports Windows® XP, Windows® Vista and Linux® in both 32- and 64-bit versions.
    * The SDK can be used from both unmanaged (C/C++) and managed (C#) applications. Documents and Samples are provided in the download package.

*Requires Catalyst 9.3 and above
What's New?

What's new in version 2.0

    * Over ten new Displays Manager APIs
    * Updated API grouping
    * Added OverDrive5 API notes
    * New sample code (DDCBlockAccess)
    * More references to constants and APIs added in the documentation
    * Bug fixes

Fractron 9000 currently uses Nvidia’s CUDA library to quickly compute fractal flames. The user interface is written in C#, and communicates with CUDA via my own custom interoperability library. Fractron uses OpenGL to display the fractals, which will hopefully make it possible to port Fractron 9000 to non-Windows platforms in the future.

Fractron 9000 renders fractals using an algorithm very closely based on the algorithm used by another program called Apophysis. As a result, future versions of Fractron 9000 may be able to load and save fractal flames generated with Apophysis.

3D-Tech News Around The Web / NVIDIA OptiX SDk and new samples available
« on: November 03, 2009, 05:14:27 PM »
NVIDIA OptiX Now Available

The OptiX engine has been in private testing at over 100 sites worldwide since the spring of 2009, with ray tracing developers already utilizing it to redefine interactive possibilities. You can join these ranks and explore how GPU ray tracing can transform your application by simply downloading the OptiX SDK and developing on standard graphics hardware. The OptiX SDK is free of charge and the engine is free to license in applications.

System Requirements

    * Operating System: 32 or 64-bit versions of Windows XP, Windows Vista, Windows 7, Linux
    * CPU: x86 compatible
    * System Memory: matches graphics board recommendations
    * GPU*: NVIDIA Quadro FX or NVIDIA Tesla (GT200 class required for multi-GPU scaling and technical support)
    * Frame buffer memory: varies with data complexity
    * Driver: NVIDIA Unified Driver r190 or later, CUDA toolkit 2.3 or later
    * C/C++ Compiler: Visual Studio 2005 or 2008, along with CMAKE

      *NVIDIA GeForce to be supported with NVIDIA's upcoming "Fermi" GPU architecture.

Pages: 1 ... 129 130 [131] 132 133 ... 149